funding-digest

Generate a polished one-page PowerPoint slide summarizing key takeaways from recent funding rounds and notable capital markets activity across a user's watched sectors or companies. Use this skill when the user asks for a deal flow summary, weekly recap, funding digest, transaction roundup, or capital markets briefing. Triggers on: 'deal flow digest', 'weekly funding recap', 'deal roundup', 'transaction summary this week', 'what happened in [sector] this week', 'capital markets update', or any request to compile recent funding activity into a briefing slide. Produces a professional single-slide PPTX with key takeaways, valuation data, and Capital IQ deal links.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a well-sequenced, validation-rich workflow and genuine domain-specific knowledge Claude lacks. Its weaknesses are conciseness (length plus redundant/self-contained code) and progressive disclosure (most detail lives inline rather than in reference files).

Suggestions

Move the detailed slide design specification (color palette, typography, table-centering math) and/or the logo-generation pipeline into separate reference files so SKILL.md reads as a lean overview pointing one level deep, lifting progressive_disclosure toward 3.

Tighten the Step 6 logo code: keep the simple-icons lookup strategy and brand-color injection specifics, but drop the boilerplate sharp/SVG code Claude can readily produce, reducing the conciseness burden.

Consolidate the AI-generated disclaimer — currently stated in the header, the footer line, and the design footer — into a single mandatory instruction to remove redundancy.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and operational (Capital IQ failure modes, aliases, exact tool params Claude lacks), but at ~510 lines it includes a full self-contained logo-generation pipeline and repeats the AI disclaimer three times, so it does not meet the "every token earns its place" bar of score 3.	2 / 3
Actionability	Provides fully executable guidance throughout — exact API calls with parameters, pptxgenjs code with concrete colW arrays and a table-centering formula, the Capital IQ URL template, and QA commands (markitdown, soffice, pdftoppm) — matching the copy-paste-ready score-3 anchor.	3 / 3
Workflow Clarity	Nine clearly sequenced steps with explicit validation checkpoints (Rule 0 pre-validation, per-batch empty-result checks, Step 8 "Fix and re-verify" cycle), satisfying the feedback-loop anchor rather than the validation-gap score-2 anchor.	3 / 3
Progressive Disclosure	The one reference present (references/sector-seeds.md) is real, well-signaled, and one level deep, but the bulk of the content — the slide design spec, the logo pipeline, and the entity-resolution rules — is inline in a monolithic 500-line SKILL.md rather than split into reference files, matching the "content that should be separate is inline" score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and rich in natural trigger terms, clearly answering both what the skill produces and when to invoke it. It carves out a distinct niche with low conflict risk, though it is somewhat verbose for a description field.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and outputs — "Generate a polished one-page PowerPoint slide summarizing key takeaways" and "Produces a professional single-slide PPTX with key takeaways, valuation data, and Capital IQ deal links" — matching the score-3 anchor of several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (generate a single-slide PPTX digest with takeaways/valuations/links) and when ("Use this skill when…" plus a "Triggers on:" list), satisfying the explicit-trigger anchor rather than the implied-when score-2 anchor.	3 / 3
Trigger Term Quality	Strong coverage of natural phrasings users would actually say — "deal flow digest", "weekly funding recap", "deal roundup", "capital markets update", "what happened in [sector] this week" — matching the good-coverage anchor rather than the partial score-2 set.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — a funding-deal briefing slide from S&P Capital IQ — with distinctive triggers unlikely to fire for unrelated skills, matching the clear-niche anchor rather than the overlapping score-2 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (514 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: anthropics/financial-services
Path: plugins/partner-built/spglobal/skills/funding-digest/SKILL.md
Commit: eb0c1ea

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.